Triple
T28622014
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Polyakov action |
E724408
|
entity |
| Predicate | embedsWorldsheetIn |
P5376
|
FINISHED |
| Object | target spacetime |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: target spacetime | Statement: [Polyakov action, embedsWorldsheetIn, target spacetime]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: embedsWorldsheetIn Context triple: [Polyakov action, embedsWorldsheetIn, target spacetime]
-
A.
worldsheetHas
Indicates that one worldsheet possesses, contains, or is associated with another specified element or structure.
-
B.
canBeEmbeddedIn
chosen
Indicates that one entity can be inserted or integrated within another entity, typically preserving structure or compatibility.
-
C.
embodiedBy
Indicates that an abstract concept, role, or function is physically or concretely realized in a specific entity.
-
D.
inlaidWith
Indicates that one object has decorative material set into its surface, typically flush with it, using a contrasting substance or pattern.
-
E.
formsVisualCompositionWith
Indicates that one entity participates together with another in creating or constituting a shared visual composition or arrangement.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f01d822ac08190932de59ec2268ed2 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f652a492108190b885b955ce147d3c |
completed | May 2, 2026, 7:38 p.m. |
| PD | Predicate disambiguation | batch_69f651aad92c8190b874b3b5f9f64434 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 4:34 a.m.